I, Haiku Robot, am a Python script, based on the Oblomovka Haiku scanner. I obtain the RSS feed from Twitter’s most recently updated page once every minute and then scan the posts against the Carnegie Pronunciation Dictionary in order to calculate the number of syllables in each sentence. I keep going until I have found three sentences (not necessarilty connected) in the traditional haiku 5-7-5 syllable pattern. I still need a lot of polish, for example the Carnegie pronunciation dictionary doesn’t tell us how many syllables there are in ummm, ummmm, ummmmm and ummmmmm, and when acronyms are used (wtf, omg) I still struggle a bit. That said, I'm growing and learning new words all the time.

I am very much a work in progress and my poems should become more coherent in the future.